Use when implementing any feature or bugfix, before writing implementation code

Use when executing implementation plans with independent tasks in the current session

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use after implementation is verified and before merge — consolidates multiple spec iterations into a single final-state report, marks related specs, and records key lessons

Use when you have a spec or requirements for a multi-step task, before touching code

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use whenever you need a decision, clarification, or approval from the user — covers how to ask with the question tool, and how to resolve the decision yourself when no user is available (question tool absent, or a [Never-Ask] response)

Guides agents through a 6-step discovery process to design and deploy Google Cloud global external Application Load Balancers with Cloud CDN, Cloud Armor, and Service Extensions, mapping workload requirements to best-practice configurations. Use when: - Designing, configuring, or deploying a Google Cloud global external Application Load Balancer, Cloud CDN, Cloud Armor WAF, or Service Extensions. - Discovering existing Google Cloud resources (Cloud Storage, MIGs, GKE, Cloud Run) to use as backends. - Generating production-grade Terraform HCL or gcloud CLI scripts for global external Application Load Balancers. - Actuating deployments via Infrastructure Manager or bash scripts, including IAM pre-checks. - Detecting, analyzing, or reconciling configuration drift on deployed global external Application Load Balancers. Don't use for: - Non-Google Cloud load balancing or security configurations. - Purely regional or internal load balancing setups (unless part of a hybrid/failover global design).

Retrieve, query, and identify relevant Google Cloud Monitoring metric descriptors for a GCP service or resource (such as Compute Engine, Spanner, BigQuery, Cloud Run, Cloud SQL, Pub/Sub, Cloud Storage, etc.). Use when asked to find, list, search, or discover GCP metric types, names, kind/value schemas, or descriptors.

Configure single-project Google Cloud Logging: regional log buckets, log sinks, log views, restricting or hiding sensitive logs in the default view (_Default) filter, IAM permissions for views (Logs View Accessor, IAM conditions), logs-based metrics, log exclusions, and sampling. Don't use for cross-project logging or multi-project setups.

Wren CLI for AI agents — a semantic SQL layer over 22+ databases (Postgres, MySQL, BigQuery, Snowflake, Spark, …). The actual workflow guides live inside the `wren` CLI itself; this is just a discovery stub. Use whenever the user asks a data question (how many, show me, top N, compare, trend, breakdown, metric, revenue, customers, orders), wants to install / set up Wren Engine, connect a new database, connect SaaS data via dlt (HubSpot, Stripe, Salesforce, GitHub, Slack), generate or regenerate an MDL project from a database schema, enrich a project with business context (enum meanings, units, cubes like ARR / DAU / churn), or turn a project's context layer into a shareable GenBI web app / dashboard and deploy it to Vercel or Cloudflare. Triggers: 'install wren', 'set up wren engine', 'connect database to wren', 'connect SaaS to wren', 'load hubspot / stripe / salesforce data', 'generate mdl', 'scaffold wren project', 'enrich wren context', 'augment my project', 'add cubes', 'build a dashboard', 'make a shareable analytics app', 'deploy my context layer as a web app', 'genbi app', 'wren onboarding', 'wren usage', 'wren generate mdl', 'wren dlt connector', 'wren enrich context', 'wren genbi'.

Augment a Wren project with business context that DB schema cannot carry — enum value meanings, units (USD vs cents, ms vs sec), NULL semantics, magic sentinels (-1 = unknown), soft-delete default filters, business synonyms, time-grain / TZ conventions, cross-system identifiers, currency rules, canonical-table preferences, AND named aggregation metrics (ARR, churn, DAU, WAU, NRR) proposed as cubes. Runs in one of two modes selected at session start: `grill` (one question at a time, user-driven) or `auto-pilot` (agent infers and applies, escalates only on conflicts and high-blast-radius additions like new cubes / views / relationships). Reads everything under <project>/raw/ (PDFs, glossaries, handbooks, code, data dictionaries) and optionally samples low-cardinality columns from the live DB (grill mode), compares against the current MDL / cubes / knowledge (rules + NL→SQL pairs), then fills gaps via the ten-category gap catalog and the cube proposal flow. Confirmed findings are written back to the right sink. Use when: user says 'enrich context', 'augment my project', 'grill me on this project', 'auto-fill my context', 'agent doesn't understand our docs / enum values / units / null meanings', 'business context is missing', 'what does status=A mean', 'is this amount in USD or cents', 'we keep getting wrong aggregations', 'add cubes for ARR / DAU / churn', 'we have a handbook / glossary / data dictionary the agent should know'; or after generating an MDL and noticing the agent lacks business semantics.

Export raw OpenTelemetry traces from an AI application to Confident AI's Observatory. TRIGGER when the user wants to send OpenTelemetry or OTLP traces/spans from an LLM app, agent, RAG pipeline, or chatbot to Confident AI; configure the Confident AI OTLP endpoint; set confident.span.* or confident.trace.* attributes; export AI-app traces without the deepeval Python package; wire an OTLPSpanExporter, OpenTelemetry Collector, or vendor-neutral OTel SDK to Confident AI; or pick the US vs EU OTLP endpoint. Language-agnostic: the mechanism is OTLP attribute keys plus an exporter endpoint. DO NOT TRIGGER for building DeepEval pytest eval suites, datasets, goldens, metrics, or deepeval test run (use the `deepeval` skill); for instrumenting with the DeepEval SDK's @observe decorator or framework integrations (use the `deepeval-tracing` skill); or for non-AI software such as web servers, CRUD backends, or infrastructure: the confident.* attributes describe AI components only.

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/stas00/ml-engineering/blob/master/SKILL.md

深度分析文档结构和内容。当用户需要分析文档结构、提取关键信息、识别文档类型、进行内容质量评估、或理解文档组织方式时使用此技能。